Fix train_rl and rl.yml paths

[ooops678]

Description

Update paths for train_rl.py and rl.yml to fix maxtext_rl DAG.

Tests

• Airflow Test Results: https://f5eac1c8d1684611864003492b988589-dot-us-east1.composer.googleusercontent.com/dags/maxtext_rl/grid?tab=logs&task_id=gspo-nightly-1xv5p-128.run_training.run_model.wait_for_workload_completion&dag_run_id=manual__2026-02-26T02%3A25%3A19.936588%2B00%3A00

Checklist

Before submitting this PR, please make sure (put X in square brackets):

• I have performed a self-review of my code.
• I have necessary comments in my code, particularly in hard-to-understand areas.
• I have run one-shot tests and provided workload links above if applicable.
• I have made or will make corresponding changes to the doc if needed.